JP2023008015A - Work site monitoring system - Google Patents

Abstract

To provide a work site monitoring system which can suppress reduction in the work efficiency of a work machine.SOLUTION: A work site monitoring system comprises: a camera 2 which photographs a work site; object detection means which detects a work machine 20 in the work site on the basis of an image captured by the camera 2; position acquisition means which acquires a position of the work machine 20 detected by the object detection means; type determination means which determines a type of the work machine 20 detected by the object detection means; work area setting means which sets a work area according to the type determined by the type determination means for the work machine 20 detected by the object detection means; and unsafe state detection means which detects the unsafe state on the basis of the position of the work machine 20 acquired by the position acquisition means and the work area set by the work area setting means.SELECTED DRAWING: Figure 1

Description

The present invention relates to a worksite monitoring system for monitoring people and work machines within a worksite.

Patent Literature 1 discloses a safety management system that prevents targets such as working machines from coming into contact with each other at a work site. In this safety management system, the entire work site is photographed by a photographing means, the contours of the working machines and workers in the work area are captured, and the target area is set. I'm trying to let you know when I deviate.

JP 2012-203677 A

By the way, at a work site, work is performed by a mixture of work machines with operators on board, remotely controlled work machines, and automatically operated work machines. Since the work contents differ for work machines with operators on board, remotely controlled work machines, and automatically operated work machines, if a uniform work area is set for multiple types of work machines, the work area Unsafe conditions such as contact with each other or deviation from the work area may be more likely to occur. In such a case, if countermeasures such as reporting or stopping the working machine are taken in response to the occurrence of the unsafe state, the working efficiency of the working machine may decrease.

SUMMARY OF THE INVENTION An object of the present invention is to provide a work site monitoring system capable of suppressing a decrease in work efficiency of a work machine.

The present invention comprises imaging means for imaging a work site, object detection means for detecting a working machine in the work site based on the image captured by the imaging means, and the working machine detected by the object detection means. position acquisition means for acquiring a position; type determination means for determining the type of the working machine detected by the object detection means; and the type determination means for determining the type of the work machine detected by the object detection means. Based on work area setting means for setting a work area according to the type, the position of the working machine acquired by the position acquisition means, and the work area set by the work area setting means, an unsafe state is determined. and unsafe state detection means for detecting.

According to the present invention, a work area corresponding to the type of work machine is set for the work machine in the work site. An unsafe condition is then detected based on the position of the work machine within the work site and the work area. Since the work area is set according to the type of work machine for multiple types of work machines, unsafe conditions can be detected more accurately than when the work area is uniformly set for multiple types of work machines. can be detected. As a result, a state that is detected as an unsafe state when a work area is uniformly set for a plurality of types of work machines may not be detected as an unsafe state. Therefore, it is not necessary to take countermeasures such as notifying or stopping the working machine more than necessary, so it is possible to suppress the deterioration of the working efficiency of the working machine.

1 is a configuration diagram of a work site monitoring system; FIG. It is a side view of a working machine. It is a figure which shows the circuit structure of a work site monitoring system and a working machine. FIG. 4 is a diagram showing a state in which a person has entered the working area of the working machine; FIG. 4 is a diagram showing a state in which the bucket has deviated from the working area of the working machine; 4 is a flowchart of monitoring control processing;

Preferred embodiments of the present invention will be described below with reference to the drawings.

(Configuration of work site monitoring system)
A worksite monitoring system according to an embodiment of the present invention monitors people and work machines within a worksite. As shown in FIG. 1, which is a configuration diagram of the work site monitoring system 1, the work site monitoring system 1 has a camera 2 and a LiDAR 3. As shown in FIG.

A plurality of cameras (imaging means) 2 are provided at the work site, and each image the work site. At a work site, a work machine 20A with an operator on board, a remotely controlled work machine 20B, and an automatically operated work machine 20C are working together. These work machines 20A to 20C are collectively referred to as work machine 20. As shown in FIG.

The remotely controlled work machine 20B is wirelessly and remotely controlled from a cockpit 71 installed at a position distant from the work machine 20B. The automatically operated work machine 20C is taught by an operator operating the tablet 72 before being automatically operated. The work content determined by the teaching information (work plan information for automatic operation) is, for example, scooping up earth and sand from the earth and sand pit 73 and discharging the earth and sand onto the loading platform of the dump truck 74 . Work plan information for automatic operation may be input to the controller of the automatically operated work machine 20C by means other than teaching.

A plurality of LiDARs (Light Detection and Ranging or Laser Imaging Detection and Ranging) 3 are provided at the work site. The LiDAR 3 acquires point cloud data indicating the distance from the position where the LiDAR 3 is attached to an object (the work machine 20 or a person) in the work site. Note that a stereo camera or a TOF (Time Of Flight) sensor may be used instead of the LiDAR3.

(Configuration of working machine)
As shown in FIG. 2, which is a side view of the working machine 20, the working machine 20 is a machine that performs work with an attachment 30, such as a hydraulic excavator. The working machine 20 has a machine main body 24 having a lower travel body 21 and an upper revolving body 22 , an attachment 30 and a cylinder 40 .

The lower traveling body 21 is a portion that allows the working machine 20 to travel, and includes, for example, crawlers. The upper revolving body 22 is rotatably attached to the upper part of the lower traveling body 21 via a revolving device 25 . A cab (driver's cab) 23 is provided in the front portion of the upper revolving body 22 .

The attachment 30 is attached to the upper rotating body 22 so as to be vertically rotatable. The attachment 30 has a boom 31 , an arm 32 and a bucket 33 . The boom 31 is attached to the upper revolving body 22 so as to be vertically rotatable (up and down). The arm 32 is attached to the boom 31 so as to be vertically rotatable. The bucket 33 is attached to the arm 32 so as to be rotatable in the front-rear direction. The bucket 33 is a part for excavating, leveling, and scooping earth and sand (transported material). The material to be transported held by the bucket 33 is not limited to earth and sand, and may be stones or waste (industrial waste, etc.).

The cylinder 40 can hydraulically rotate the attachment 30 . The cylinder 40 is a hydraulic telescopic cylinder. The cylinder 40 includes a boom cylinder 41 , an arm cylinder 42 and a bucket cylinder 43 .

The boom cylinder 41 rotates the boom 31 with respect to the upper swing body 22 . A base end portion of the boom cylinder 41 is rotatably attached to the upper swing body 22 . A tip portion of the boom cylinder 41 is rotatably attached to the boom 31 .

Arm cylinder 42 rotates arm 32 with respect to boom 31 . A base end of the arm cylinder 42 is rotatably attached to the boom 31 . A tip portion of the arm cylinder 42 is rotatably attached to the arm 32 .

The bucket cylinder 43 rotates the bucket 33 with respect to the arm 32 . A base end of the bucket cylinder 43 is rotatably attached to the arm 32 . A tip portion of the bucket cylinder 43 is rotatably attached to a link member 34 rotatably attached to the bucket 33 .

The work machine 20 also has an angle sensor 52 and an inclination sensor 60 .

The angle sensor 52 detects the turning angle of the upper turning body 22 with respect to the lower traveling body 21 . The angle sensor 52 is, for example, an encoder, resolver, or gyro sensor. In this embodiment, the turning angle of the upper turning body 22 when the front of the upper turning body 22 coincides with the front of the lower traveling body 21 is 0°.

The tilt angle sensor 60 detects the orientation of the attachment 30 . The tilt angle sensor 60 includes a boom tilt angle sensor 61 , an arm tilt angle sensor 62 and a bucket tilt angle sensor 63 .

A boom tilt angle sensor 61 is attached to the boom 31 and detects the attitude of the boom 31 . The boom tilt angle sensor 61 is a sensor that acquires the tilt angle of the boom 31 with respect to the horizontal line, and is, for example, a tilt (acceleration) sensor. The boom tilt angle sensor 61 may be a rotation angle sensor that detects the rotation angle of the boom foot pin (boom base end) or a stroke sensor that detects the stroke amount of the boom cylinder 41 .

The arm tilt angle sensor 62 is attached to the arm 32 and detects the posture of the arm 32 . The arm tilt angle sensor 62 is a sensor that acquires the tilt angle of the arm 32 with respect to the horizontal line, and is, for example, a tilt (acceleration) sensor. The arm tilt angle sensor 62 may be a rotation angle sensor that detects the rotation angle of the arm connecting pin (arm proximal end) or a stroke sensor that detects the stroke amount of the arm cylinder 42 .

The bucket tilt angle sensor 63 is attached to the link member 34 and detects the attitude of the bucket 33 . The bucket tilt angle sensor 63 is a sensor that acquires the tilt angle of the bucket 33 with respect to the horizontal line, and is, for example, a tilt (acceleration) sensor. The bucket tilt angle sensor 63 may be a rotation angle sensor that detects the rotation angle of the bucket connecting pin (bucket proximal end) or a stroke sensor that detects the stroke amount of the bucket cylinder 43 .

(Circuit Configuration of Work Site Monitoring System and Working Machine)
As shown in FIG. 3, which is a diagram showing the circuit configuration of the work site monitoring system 1 and the work machine 20, the work machine 20 includes a work machine controller 81, a work machine storage device 82, and a work machine communication device 83. and have

Information about the turning angle (attitude) of the upper turning body 22 with respect to the lower traveling body 21 detected by the angle sensor 52 is input to the work machine controller 81 . Further, information regarding the attitude of the boom 31 detected by the boom tilt angle sensor 61 is input to the work machine controller 81 . Further, information regarding the attitude of the arm 32 detected by the arm tilt angle sensor 62 is input to the work machine controller 81 . Further, information regarding the posture of the bucket 33 detected by the bucket tilt angle sensor 63 is input to the work machine controller 81 .

In the case of the automatically operated work machine 20C, the work machine storage device 82 stores teaching information. In the case of the work machine 20</b>C that is automatically operated, the work machine controller 81 operates the attachment 30 and the turning device 25 based on the teaching information stored in the work machine storage device 82 .

The work machine side communication device 83 can communicate with a communication device 8 of the work site monitoring system 1, which will be described later.

The work site monitoring system 1 includes a controller 5 , a storage device 6 and a communication device 8 . The communication device 8 can communicate with the work machine side communication device 83 of the work machine 20 .

The controller 5 has an object detection section 11 , a position acquisition section 12 , a type determination section 13 , a work area setting section 14 and an unsafe state detection section 15 .

The object detection unit (object detection means) 11 detects the work machine 20 in the work site based on the image captured by the camera 2 . Also, the object detection unit 11 detects a person in the work site based on the image captured by the camera 2 . Deep learning technology or the like may be used to detect work machine 20 and people.

A position acquisition unit (position acquisition means) 12 acquires the position of the work machine 20 detected by the object detection unit 11 . Also, the position acquisition unit 12 acquires the position of the person detected by the object detection unit 11 . Specifically, the position acquisition unit 12 uses the position (coordinates) of the global coordinate system to which the LiDAR 3 is attached and the distance from the LiDAR 3 to each point of the point cloud data to obtain the point cloud data in the global coordinate system. The position (three-dimensional coordinates) of each point of is calculated. Next, the position acquisition unit 12 performs perspective projection transformation on the three-dimensional coordinates of each point of the point cloud data to acquire two-dimensional coordinates of each point of the point cloud data. Then, the position acquisition unit 12 superimposes the two-dimensional coordinates of each point of the point cloud data on the two-dimensional image captured by the camera 2 . Then, the position acquisition unit 12 obtains the positions of the work machine 20 and the person detected by the object detection unit 11 from the three-dimensional coordinates of the points overlapping the work machine 20 and the person detected by the object detection unit 11 in the point cloud data. Get in three dimensions.

Here, the position of the global coordinate system to which the camera 2 and the LiDAR 3 are attached is acquired by a positioning sensor such as a GNSS sensor or a distance measuring sensor such as a total station.

The type determination unit (type determination means) 13 determines the type of the working machine 20 detected by the object detection unit 11 . As shown in FIG. 1, the color of the lamp provided on the work machine 20 is used to determine the type of the work machine 20 . A red lamp R and a yellow lamp Y are attached to the work machine 20A on which the operator is mounted. A red lamp R, a yellow lamp Y, and a green lamp G are attached to the remotely controlled work machine 20B. A red lamp R, a yellow lamp Y, and a blue lamp B are attached to the automatically operated work machine 20C. The type of work machine 20 is determined from the colors of these lamps.

Returning to FIG. 3 , the work area setting section (work area setting means) 14 sets a work area for each work machine 20 detected by the object detection section 11 . Here, the work area setting unit 14 sets the work area according to the type of the work machine 20 determined by the type determination unit 13 .

For example, the work area of the work machine 20A with the operator on board is wider than the work area of the remotely operated work machine 20B and the work area of the automatically operated work machine 20C in consideration of the operator's degree of freedom in operation. set. The work area of the automatically operated work machine 20C is set narrower than the work area of the remotely controlled work machine 20B, considering that the work content of the work machine 20C is determined by teaching.

An unsafe state detection unit (unsafe state detection means) 15 detects an unsafe state based on the position of the working machine 20 acquired by the position acquisition unit 12 and the work area set by the work area setting unit 14. . Moreover, the unsafe state detection unit 15 detects an unsafe state based on the position of the person acquired by the position acquisition unit 12 and the work area set by the work area setting unit 14 .

Here, the unsafe state includes a state in which work machine 20 has entered the work area. Also, the unsafe state includes a state in which a person has entered the work area. FIG. 4 shows a state in which a person has entered the work area. In FIG. 4 , a person 95 has entered the work area 90 of the work machine 20 .

In addition, the unsafe state includes a state in which the machine body of work machine 20 has deviated from its work area. FIG. 5 shows a state in which the machine body of the work machine 20 has deviated from its work area. In FIG. 5 , bucket 33 is deviated from work area 90 of work machine 20 .

Returning to FIG. 3 , the controller 5 has an unsafe level determination section 16 and a countermeasure control section 17 . The non-safety level determination section (non-safety level determination means) 16 determines the non-safety level based on the non-safety state detected by the non-safety state detection section 15 . In this embodiment, as shown in Table 1 below, the non-safety levels are classified into three levels of "high", "middle", and "low". The greater the unsafe level, the greater the human damage.

For example, in the case of a collision between the remotely controlled work machine 20B and the automatically operated work machine 20C, in which no human injury occurs, the non-safety level is determined to be "small". In addition, the operator and the person or the operators each avoid collisions, such as the collision between the work machine 20A on which the operator is on board and a person, or the collision between the work machine 20A on which the operator is on board and the work machine 20C during teaching. In the case where it is possible to make such a judgment as to prevent human injury, the non-safety level is judged to be "medium". In addition, when the collision cannot be avoided only by the judgment of the person or the operator, such as the collision between the automatically operated working machine 20C and the human, or the collision between the remotely controlled working machine 20B and the working machine 20A on which the operator is on board. If there is a risk of human injury, the non-safety level is determined to be "high".

Note that the non-safety level may be set according to the work content of the work machine 20 . For example, if the work is to swing the attachment 30, the work area is widened, so the non-safety level is set to "high". Also, when the work is excavation, the work area is narrow, so the unsafe level is set to "small".

The countermeasure control unit (control means) 17 performs at least one of warning and stopping of the work machine 20 according to the non-safety level determined by the non-safety level determination unit 16 . In this embodiment, when the non-safety level is "small", an external warning is issued. Further, when the non-safety level is "medium", a warning is given to the outside and the work of the work machine 20 is stopped (the engine is not stopped). Also, when the non-safety level is "high", the engine of the work machine 20 is stopped.

A warning to the outside is generated from a warning device. The warning device is a display or speaker provided in the cockpit 71 or the work machine 20 . An operator who operates the cockpit 71 may be able to avoid a collision between the work machines 20 by changing the operation of the remotely controlled work machine 20B in response to the warning. Also, the operator of the work machine 20A on which the operator is on board may be able to avoid a collision between the work machines 20 by changing the operation of the work machine 20A in response to the warning.

The work stop of the work machine 20 is performed by transmitting a work stop instruction from the communication device 8 to the relevant work machine 20 . Upon receiving the work stop instruction, the work machine controller 81 temporarily stops the operations of the attachment 30 and the swing device 25 . As a result, a collision between the work machine 20 and a person or a collision between the work machines 20 may be avoided.

The engine stop of the work machine 20 is performed by transmitting an engine stop instruction from the communication device 8 to the relevant work machine 20 . The work machine controller 81 that has received the instruction to stop the engine stops the engine (not shown). As a result, a collision between the work machine 20 and a person or a collision between the work machines 20 may be avoided.

Here, as described above, a work area corresponding to the type of work machine 20 is set for a plurality of types of work machine 20 . Therefore, an unsafe state can be detected more accurately than when a work area is uniformly set for a plurality of types of work machines 20 . As a result, a state that is detected as an unsafe state when a work area is uniformly set for a plurality of types of work machines 20 may no longer be detected as an unsafe state. Therefore, it is not necessary to take countermeasures such as notifying or stopping the work machine 20 more than necessary, so that the work efficiency of the work machine 20 can be suppressed.

Further, as shown in FIG. 4, when a person or the work machine 20 intrudes into the work area, by taking countermeasures such as reporting or stopping the work machine 20, collision between the person and the work machine 20 can be prevented. In some cases, collisions between machines 20 can be avoided. Further, as shown in FIG. 5, when the machine body of the work machine 20 deviates from its own work area, by taking countermeasures such as reporting and stopping the work machine 20, collisions between people and the work machine 20, Collisions between the work machines 20 can be avoided in some cases.

Here, the work area setting unit 14 shown in FIG. 3 sets the work area for the automatically operated work machine 20C based on the teaching information. The work content of the automatically operated work machine 20C is determined by teaching information. Therefore, by setting the work area based on the teaching information, the unsafe state can be detected more accurately.

Further, the work area setting unit 14 sets a work area for the automatically operated work machine 20C based on whether or not an operator is on the work machine 20C. It is determined from an image captured by the camera (determining means) 2 whether or not an operator is on the automatically operated work machine 20C. Note that a camera may be installed inside the cab 23 of the automatically operated work machine 20C to determine whether or not there is an operator inside the cab 23 . Alternatively, a thermosensor may be provided inside the cab 23 to determine whether or not there is an operator inside the cab 23 . Further, a sensor may be provided in the cockpit inside the cab 23 to determine whether or not the operator is sitting in the cockpit.

For example, when an operator is on board the automatically operated work machine 20C and is performing teaching, etc., considering the degree of freedom of the operator's operation, the operator is not on the automatically operated work machine 20C. Also, set a wider work area. As a result, the unsafe state can be detected more accurately than in the case where the work area is uniformly set regardless of whether the operator is on board.

Further, the storage device 6 stores the work contents of the work machine 20A on which the operator is on board and the work machine 20B that is remotely controlled. The work area setting unit 14 sets a work area based on the work contents stored in the storage device 6 for each of the work machine 20A with the operator on board and the remotely controlled work machine 20B.

The work performed by the work machine 20A with the operator on board and the remotely controlled work machine 20B is often repetitive work. By storing such work contents in the storage device 6 and setting the work area based on this, the work area can be narrowed down. As a result, an unsafe state can be detected more accurately than when the work area is not narrowed down.

In addition, the non-safety level determination unit (output means) 16 causes the communication device 8 to output its own determination result to the outside every predetermined period. The output destination of the determination result is the cockpit 71, a server (not shown), or the like. The server is a management server or the like that manages the entire construction site. The predetermined period is, for example, one day or one week. The determination results include the number of occurrences and types of unsafe levels. By using this determination result, it is possible to take measures such as thorough safety at the work site.

(Operation of work site monitoring system)
Next, the operation of the work site monitoring system 1 will be described with reference to FIG. 6, which is a flowchart of the monitoring control process.

First, the controller 5 of the work site monitoring system 1 performs initial setting (step S1). Specifically, camera calibration of the camera 2 is performed. Camera calibration is to determine and correct the mounting position of the camera 2, the mounting angle of the camera 2, the distortion of the lens of the camera, the focal length of the lens of the camera 2, and the like. Also, calibration is performed between the camera 2 and the LiDAR 3 . This calibration is a process of associating the coordinates on the image captured by the camera 2 with the coordinates on the point cloud data acquired by the LiDAR 3 .

Next, the controller 5 corrects the relative position (step S2). Specifically, the point cloud data acquired by the LiDAR 3 is projected onto the image captured by the camera 2 to correct the relative position.

Next, the controller 5 acquires position information (step S3). Specifically, the positions of the camera 2 and the LiDAR 3 in the global coordinate system are acquired using a positioning sensor or the like.

Next, controller 5 corrects the three-dimensional coordinates of camera 2 and LiDAR 3 (step S4).

Next, the controller 5 takes in the image captured by the camera 2 and the point cloud data acquired by the LiDAR 3 (step S5). The object detection unit 11 of the controller 5 detects a person and the work machine 20 within the work site based on the image captured by the camera 2 . Then, the position acquisition unit 12 of the controller 5 acquires the positions of the person and the working machine 20 detected by the object detection unit 11 (step S6).

Next, the type determination unit 13 of the controller 5 determines the type of the work machine 20 detected by the object detection unit 11 (step S7). The work area setting unit 14 of the controller 5 sets a work area for each work machine 20 detected by the object detection unit 11 (step S8).

Next, the unsafe state detection unit 15 of the controller 5 determines whether or not an unsafe state has been detected (step S9). If it is determined in step S9 that an unsafe state has not been detected (S9: NO), the controller 5 proceeds to step S17. On the other hand, if it is determined in step S9 that an unsafe state has been detected (S9: YES), the unsafe level determining section 16 of the controller 5 determines an unsafe level (step S10).

Next, the countermeasure control unit 17 of the controller 5 determines whether or not the unsafe level is "high" (step S11). In step S11, when the non-safety level is "high" (S11: YES), the countermeasure control unit 17 transmits an instruction to stop the engine to the corresponding work machine 20 (step S12). The work machine 20 that has received the instruction to stop the engine stops the engine. Then, the process proceeds to step S17.

On the other hand, in step S11, if the non-safety level is not "high" (S11: NO), the countermeasure control unit 17 determines whether or not the non-safety level is "middle" (step S13). In step S13, if the non-safety level is "medium" (S13: YES), the countermeasure control unit 17 issues a warning from the warning device and transmits a work stop instruction to the relevant work machine 20. (Step S14). The work machine 20 that has received the work stop instruction temporarily stops the operations of the attachment 30 and the turning device 25 . Then, the process proceeds to step S17.

On the other hand, in step S13, when the non-safety level is not "middle" (S13: NO), the countermeasure control unit 17 determines that the non-safety level is "low" (step S15). Then, the countermeasure control unit 17 issues a warning from the warning device (step S16). Then, the process proceeds to step S17.

At step S17, the controller 5 updates the work content stored in the storage device 6 (step S17). As a result, in step S8, the work area setting unit 14 resets the work contents for each of the work machine 20A on which the operator is on board and the remotely controlled work machine 20B. Then, the process returns to step S8.

(Modification)
Note that, in this embodiment, the positions of objects (the working machine 20 and people) in the work site are acquired in three dimensions, and an unsafe state is detected from the relationship between these and the work area. However, the positions of objects (work machine 20 and people) in the work site may be obtained two-dimensionally, and the unsafe state may be detected from the relationship between these and the work area.

(effect)
As described above, according to the work site monitoring system 1 according to the present embodiment, a work area corresponding to the type of the work machine 20 is set for the work machine 20 in the work site. An unsafe condition is then detected based on the position of work machine 20 within the work site and the work area. Since the work area corresponding to the type of the work machine 20 is set for the plurality of types of work machines 20, compared to the case where the work area is uniformly set for the plurality of types of work machines 20, it is unsafe. The state can be detected accurately. As a result, a state that is detected as an unsafe state when a work area is uniformly set for a plurality of types of work machines 20 may no longer be detected as an unsafe state. Therefore, it is not necessary to take countermeasures such as notifying or stopping the work machine 20 more than necessary, so that the work efficiency of the work machine 20 can be suppressed.

Unsafe conditions are also detected based on the location of people within the work site and the work area. At this time, since work areas corresponding to the types of work machines 20 are set for a plurality of types of work machines 20, compared to the case where work areas are uniformly set for a plurality of types of work machines 20, can accurately detect an unsafe condition. As a result, a state that is detected as an unsafe state when a work area is uniformly set for a plurality of types of work machines 20 may no longer be detected as an unsafe state. Therefore, it is not necessary to take countermeasures such as notifying or stopping the work machine 20 more than necessary, so that the work efficiency of the work machine 20 can be suppressed.

Also, a state in which a person has entered the work area is detected as an unsafe state. In such a case, it may be possible to prevent a collision between a person and the work machine 20 by taking countermeasures such as reporting or stopping the work machine 20 .

Moreover, a state in which the work machine 20 has entered the work area is detected as an unsafe state. In such a case, it may be possible to prevent collisions between the work machines 20 by taking countermeasures such as reporting or stopping the work machines 20 .

In addition, a state in which the body of work machine 20 deviates from its own work area is detected as an unsafe state. In such a case, it may be possible to prevent a collision between a person and the work machine 20 or a collision between the work machines 20 by taking countermeasures such as reporting or stopping the work machine 20 .

Also, at least one of a warning and a stop of work machine 20 is performed according to the unsafe level. For example, in the case of a collision between the remotely controlled work machine 20B and the automatically operated work machine 20C, in the case of an unsafe level that does not cause human damage, by giving a warning, the work machines 20 can communicate with each other. collision can be avoided. In addition, for example, in the case of a non-safety level such as a collision between the work machine 20 and a person, by stopping the work machine 20, the collision between the work machine 20 and a person can be prevented. Sometimes it can be avoided.

In addition, a work area is set for the automatically operated work machine 20C based on teaching information (work plan information for automatic operation). The work content of the automatically operated work machine 20C is determined by teaching information. Therefore, by setting the work area based on the teaching information, the unsafe state can be detected more accurately.

Further, a work area is set for the automatically operated work machine 20C based on the determination result of whether or not an operator is on board. For example, when an operator is on board the automatically operated work machine 20C and is performing teaching, etc., considering the degree of freedom of the operator's operation, the operator is not on the automatically operated work machine 20C. Also, set a wider work area. As a result, the unsafe state can be detected more accurately than in the case where the work area is uniformly set regardless of whether the operator is on board.

A work area is set for each of the work machine 20A on which the operator is on board and the remotely controlled work machine 20B based on the work content stored in the storage device 6 . The work performed by the work machine 20A with the operator on board and the remotely controlled work machine 20B is often repetitive work. By storing such work contents in the storage device 6 and setting the work area based on this, the work area can be narrowed down. As a result, an unsafe state can be detected more accurately than when the work area is not narrowed down.

Moreover, the determination result of the non-safety level determination unit 16 is output to the outside every predetermined period. By using this determination result, it is possible to take measures such as thorough safety at the work site.

Although the embodiments of the present invention have been described above, the specific examples are merely illustrated, and the present invention is not particularly limited. Further, the actions and effects described in the embodiments of the invention are merely enumerations of the most suitable actions and effects resulting from the present invention, and the actions and effects of the present invention are described in the embodiments of the invention. are not limited to those listed.

1 work site monitoring system 2 camera (imaging means, determination means)
3 LiDAR
5 controller 6 storage device 8 communication device 11 object detection unit (object detection means)
12 Position Acquisition Unit (Position Acquisition Means)
13 type discriminating unit (type discriminating means)
14 work area setting unit (work area setting means)
15 unsafe state detection unit (unsafe state detection means)
16 Non-safety level judgment unit (non-safety level judgment means, output means)
17 countermeasure control unit (control means)
20 working machine 21 undercarriage 22 upper swing body 23 cab 24 machine body 25 swing device 30 attachment 31 boom 32 arm 33 bucket 34 link member 40 cylinder 41 boom cylinder 42 arm cylinder 43 bucket cylinder 52 angle sensor 60 tilt angle sensor 61 boom Tilt angle sensor 62 Arm tilt angle sensor 63 Bucket tilt angle sensor 71 Cockpit 72 Tablet 73 Earth and sand pit 74 Dump 81 Working machine side controller 82 Working machine side storage device 83 Working machine side communication device 90 Work area 95 people

Claims (10)

imaging means for imaging a work site;
an object detection means for detecting a working machine in the work site based on the image captured by the imaging means;
position acquisition means for acquiring the position of the work machine detected by the object detection means;
a type discriminating means for discriminating the type of the working machine detected by the object detecting means;
work area setting means for setting a work area according to the type determined by the type determination means for the work machine detected by the object detection means;
Unsafe state detection means for detecting an unsafe state based on the position of the work machine acquired by the position acquisition means and the work area set by the work area setting means;
A work site monitoring system comprising: The object detection means detects a person in the work site,
The position acquisition means acquires the position of the person detected by the object detection means,
The unsafe state detecting means detects the unsafe state based on the position of the person acquired by the position acquiring means and the work area set by the work area setting means. Item 1. The work site monitoring system according to item 1. 3. The work site monitoring system according to claim 2, wherein the unsafe state includes a state in which the person has entered the work area. The work site monitoring system according to any one of claims 1 to 3, wherein the unsafe state includes a state in which the work machine has entered the work area. The work site monitoring system according to any one of claims 1 to 4, wherein the unsafe state includes a state in which the machine body of the working machine has deviated from its own work area. Unsafe level determination means for determining an unsafe level based on the unsafe state;
a control means for at least one of warning and stopping the work machine according to the unsafe level;
The work site monitoring system according to any one of claims 1 to 5, characterized by comprising: The types of the working machine include the working machine that is automatically operated,
7. The work area setting means according to any one of claims 1 to 6, wherein the work area setting means sets the work area for the automatically operated work machine based on work plan information for automatic operation. worksite monitoring system. Determination means for determining whether or not the operator is on board the work machine that is automatically operated,
8. The work site monitoring system according to claim 7, wherein the work area setting means sets the work area for the automatically operated work machine based on the determination result of the determination means. The types of the work machine include the work machine with an operator on board and the work machine that is remotely controlled,
a storage device for storing work contents of the work machine on which the operator is on board and the work of the work machine that is remotely controlled;
The work area setting means sets the work area based on the work contents stored in the storage device for each of the work machine on which the operator is on board and the work machine that is remotely controlled. The work site monitoring system according to any one of claims 1 to 8, characterized by: Unsafe level determination means for determining an unsafe level based on the unsafe state;
output means for outputting the determination result of the non-safety level determination means to the outside every predetermined period;
The work site monitoring system according to any one of claims 1 to 9, characterized by comprising:

Images